Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
69 posts
Debate (AI safety technique)
Factored Cognition
Experiments
Ought
AI-assisted Alignment
Memory and Mnemonics
Air Conditioning
43 posts
Iterated Amplification
Humans Consulting HCH
46
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
11
Research request (alignment strategy): Deep dive on "making AI solve alignment for us"
JanBrauner
19d
3
79
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
84
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
118
Godzilla Strategies
johnswentworth
6mo
65
3
Alignment with argument-networks and assessment-predictions
Tor Økland Barstad
7d
3
80
Air Conditioner Test Results & Discussion
johnswentworth
6mo
38
116
Supervise Process, not Outcomes
stuhlmueller
8mo
8
106
Preregistration: Air Conditioner Test
johnswentworth
8mo
64
28
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
27
Briefly thinking through some analogs of debate
Eli Tyre
3mo
3
18
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
8
Infinite Possibility Space and the Shutdown Problem
magfrump
2mo
0
45
Scientific Wrestling: Beyond Passive Hypothesis-Testing
adamShimi
9mo
6
50
Notes on OpenAI’s alignment plan
Alex Flint
12d
5
132
Debate update: Obfuscated arguments problem
Beth Barnes
1y
21
68
Garrabrant and Shah on human modeling in AGI
Rob Bensinger
1y
10
117
My Understanding of Paul Christiano's Iterated Amplification AI Safety Research Agenda
Chi Nguyen
2y
21
11
Surprised by ELK report's counterexample to Debate, IDA
Evan R. Murphy
4mo
0
85
Model splintering: moving from one imperfect model to another
Stuart_Armstrong
2y
10
48
HCH Speculation Post #2A
Charlie Steiner
1y
7
60
Relating HCH and Logical Induction
abramdemski
2y
4
111
Paul's research agenda FAQ
zhukeepa
4y
73
61
Relaxed adversarial training for inner alignment
evhub
3y
28
12
HCH and Adversarial Questions
David Udell
10mo
7
32
Universality Unwrapped
adamShimi
2y
2
56
Directions and desiderata for AI alignment
paulfchristiano
3y
1
37
Synthesizing amplification and debate
evhub
2y
10